{ "openapi": "3.0.1", "info": { "title": "AI Web Scraper - Powered by Crawl4AI", "description": "A blazing-fast AI web scraper powered by Crawl4AI. Perfect for LLMs, AI agents, AI automation, model training, sentiment analysis, and content generation. Supports deep crawling, multiple extraction strategies and flexible output (Markdown/JSON). Seamlessly integrates with Make.com, n8n, and Zapier.", "version": "0.0", "x-build-id": "yLnHaI297EvKjolLE" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/raizen~ai-web-scraper/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-raizen-ai-web-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for its completion, and returns Actor's dataset items in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/raizen~ai-web-scraper/runs": { "post": { "operationId": "runs-sync-raizen-ai-web-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK", "content": { "application/json": { "schema": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/raizen~ai-web-scraper/run-sync": { "post": { "operationId": "run-sync-raizen-ai-web-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } } }, "components": { "schemas": { "inputSchema": { "type": "object", "required": [ "startUrls" ], "properties": { "startUrls": { "title": "URLs to Scrape", "type": "array", "description": "List of webpages to scrape.", "items": { "type": "object", "required": [ "url" ], "properties": { "url": { "type": "string", "title": "URL of a web page", "format": "uri" } } } }, "extractionStrategy": { "title": "Extraction Strategy", "enum": [ "SimpleExtractionStrategy", "LLMExtractionStrategy", "JsonCssExtractionStrategy", "JsonXPathExtractionStrategy" ], "type": "string", "description": "Select how content is extracted.", "default": "SimpleExtractionStrategy" }, "crawlStrategy": { "title": "Crawl Strategy", "enum": [ "SimpleCrawlStrategy", "BFSDeepCrawlStrategy", "DFSDeepCrawlStrategy", "BestFirstCrawlingStrategy" ], "type": "string", "description": "Select how pages are crawled.", "default": "SimpleCrawlStrategy" }, "browserConfig": { "title": "Browser Configuration", "type": "object", "description": "Browser settings as JSON object." }, "crawlerConfig": { "title": "Crawler Configuration", "type": "object", "description": "Crawler settings as JSON object." }, "deepCrawlConfig": { "title": "Deep Crawl Configuration", "type": "object", "description": "Settings for deep crawling when using BFS, DFS, or Best-First Strategies." }, "markdownConfig": { "title": "Markdown Generator Configuration", "type": "object", "description": "Markdown settings as JSON object." }, "contentFilterConfig": { "title": "Content Filter Configuration", "type": "object", "description": "Content filter settings as JSON object." }, "userAgentConfig": { "title": "User Agent Configuration", "type": "object", "description": "User agent settings for browser requests." }, "llmConfig": { "title": "LLM Configuration", "type": "object", "description": "Configure LLM usage for content extraction." }, "extractionSchema": { "title": "Extraction Schema", "type": "object", "description": "Define custom extraction rules when using JsonCssExtractionStrategy or JsonXPathExtractionStrategy." }, "session_id": { "title": "Session ID", "type": "string", "description": "Use a session ID to persist browser state across multiple requests.", "default": "" } } }, "runsResponseSchema": { "type": "object", "properties": { "data": { "type": "object", "properties": { "id": { "type": "string" }, "actId": { "type": "string" }, "userId": { "type": "string" }, "startedAt": { "type": "string", "format": "date-time", "example": "2025-01-08T00:00:00.000Z" }, "finishedAt": { "type": "string", "format": "date-time", "example": "2025-01-08T00:00:00.000Z" }, "status": { "type": "string", "example": "READY" }, "meta": { "type": "object", "properties": { "origin": { "type": "string", "example": "API" }, "userAgent": { "type": "string" } } }, "stats": { "type": "object", "properties": { "inputBodyLen": { "type": "integer", "example": 2000 }, "rebootCount": { "type": "integer", "example": 0 }, "restartCount": { "type": "integer", "example": 0 }, "resurrectCount": { "type": "integer", "example": 0 }, "computeUnits": { "type": "integer", "example": 0 } } }, "options": { "type": "object", "properties": { "build": { "type": "string", "example": "latest" }, "timeoutSecs": { "type": "integer", "example": 300 }, "memoryMbytes": { "type": "integer", "example": 1024 }, "diskMbytes": { "type": "integer", "example": 2048 } } }, "buildId": { "type": "string" }, "defaultKeyValueStoreId": { "type": "string" }, "defaultDatasetId": { "type": "string" }, "defaultRequestQueueId": { "type": "string" }, "buildNumber": { "type": "string", "example": "1.0.0" }, "containerUrl": { "type": "string" }, "usage": { "type": "object", "properties": { "ACTOR_COMPUTE_UNITS": { "type": "integer", "example": 0 }, "DATASET_READS": { "type": "integer", "example": 0 }, "DATASET_WRITES": { "type": "integer", "example": 0 }, "KEY_VALUE_STORE_READS": { "type": "integer", "example": 0 }, "KEY_VALUE_STORE_WRITES": { "type": "integer", "example": 1 }, "KEY_VALUE_STORE_LISTS": { "type": "integer", "example": 0 }, "REQUEST_QUEUE_READS": { "type": "integer", "example": 0 }, "REQUEST_QUEUE_WRITES": { "type": "integer", "example": 0 }, "DATA_TRANSFER_INTERNAL_GBYTES": { "type": "integer", "example": 0 }, "DATA_TRANSFER_EXTERNAL_GBYTES": { "type": "integer", "example": 0 }, "PROXY_RESIDENTIAL_TRANSFER_GBYTES": { "type": "integer", "example": 0 }, "PROXY_SERPS": { "type": "integer", "example": 0 } } }, "usageTotalUsd": { "type": "number", "example": 0.00005 }, "usageUsd": { "type": "object", "properties": { "ACTOR_COMPUTE_UNITS": { "type": "integer", "example": 0 }, "DATASET_READS": { "type": "integer", "example": 0 }, "DATASET_WRITES": { "type": "integer", "example": 0 }, "KEY_VALUE_STORE_READS": { "type": "integer", "example": 0 }, "KEY_VALUE_STORE_WRITES": { "type": "number", "example": 0.00005 }, "KEY_VALUE_STORE_LISTS": { "type": "integer", "example": 0 }, "REQUEST_QUEUE_READS": { "type": "integer", "example": 0 }, "REQUEST_QUEUE_WRITES": { "type": "integer", "example": 0 }, "DATA_TRANSFER_INTERNAL_GBYTES": { "type": "integer", "example": 0 }, "DATA_TRANSFER_EXTERNAL_GBYTES": { "type": "integer", "example": 0 }, "PROXY_RESIDENTIAL_TRANSFER_GBYTES": { "type": "integer", "example": 0 }, "PROXY_SERPS": { "type": "integer", "example": 0 } } } } } } } } } }